Skip to main content

QROWD - Because Big Data Integration is Humanly Possible


Urban mobility dashboard

This prototype will be the first outcome of T2.3. The Dashboard will allow the Municipality of Trento (as well as any other operator deploying the QROWD) to monitor in real-time data streams collected from various sources (existing infrastructure, crowds) as well as the integrated, combined, and cleansed data transmitted to end users. The application also collects and displays statistics on traffic and the usage of various means of transport, allowing for the analysis and evaluation of the impact of the QROWD system.

Data storage and access component

This report includes the application and services created to enable a crowdsourced curation for disambiguating named entities and validation of uniqueness in the storage.

Road information services

This deliverable will deliver an MVP for the road information service prototype including underlying algorithms and datasets. This will include work on analytics about road information. A prototype user interface will be developed for experts working at TomTom. It will allow exploration of the data and pattern detection. Spatiotemporal patterns will be matched and enrich the pattern catalogue at TomTom. On top of data analysis, several classifiers will be built, which can recognize specific traffic situations. Detected situations can then be included as features in regular machine learning procedures.

Crowdsourced multilingual data harvesting and extraction framework

This prototype will be the outcome of T4.4. Starting from existing NLP frameworks, the prototype will consist in a crowdsourced enhanced multilingual data harvesting and extraction system that will be able to, starting from a set of relevant textual information sources identified in D4.1, generate an RDF stream to inject into the QROWD platform.

Real-time inductive analysis

In this deliverable, we describe the foundations on how the supervised machine learning algorithms can be extended for active crowdsourcing and provide a connection between visual analysis and supervised machine learning on top of which supervised machine learning experiments covering at least the parking business case will be performed.

Data acquisition framework

This prototype will be the outcome of T4.2 and will consist of a set of tools that, according to D4.1 specifications, are able to automatically acquire data for several heterogeneous data sources relevant to the QROWD business cases and make them available for posterior RDF-ization.

Linked Data generation framework

This prototype is the outcome of T4.3 and will consist of a set of tools that, according to D4.1 specifications, are able to generate RDF streams and make them available for QROWD Big Data Value Chain.

Integrated processing of data-in-motion and data-at-rest

Architectural design and prototype for integrated processing of data-at-rest and data-in-motion, including initial evaluation.

Spatio-temporal analytics

Analytics suite supporting large-scale distributed spatiotemporal and structured data stream processing, evaluated together with WP1 and 2.


This prototype will be the second outcome of T2.3. It will consist of a deployment of the extended iLog app, an application that will be used as one of the main sources of data key to the success of the business case. iLog crowdsourcing app will be significantly extended allow for harvesting crowdsourced data. The following aspects ofiLog will be enhanced new modality-of use contribution; the ability to display different information.

QROWD platform

Final integrated QROWD platform where the business case feedback is considered.

Crowdsourcing services

Crowdsourcing middleware prototype.

Methods for task and time management

Report to document advanced methods for the optimization of crowdsourcing results, integrated into D3.2 prototype, and evaluated with the help of the business cases.

Final Trento pilot

This deliverable will assess the overall impact of the QROWD system, and in particular of the enhanced sensoRcivico app within the business case implementation, including comparison with the previous status of the Trento mobility services and assessment of the KPIs.

Outreach report v1

Strategy, channels use, results for the first reporting period, including contributions to BDV PPP and data interoperability and standards activities.

Dynamic data integration, storage and access

This will be the report on architecture and data integration tasks carried out to enable data access by the third-party applications. Curation-wise, it prepares the actual data to be available from the platform to the business pilots.

Final TomTom pilot

The report will deliver the deployed prototype, including evaluation results.

Business case requirements and design

This deliverable will report on the results of business case requirements and design (T2.1). It will enclose the requirements and design for the business case, including required and identified datasets (and transformations, if needed), requirements applicable to WP3-WP8 and business case specific requirements. It will include a detailed description of QROWD platform usage (and tailoring, if needed), any business case specific software components (if needed) and will guide the evaluation phase. We will take into account the insights gained from T2.2

Outreach report v2

Final version including impact assessment, including reports on contributions to BDV PPP and data interoperability and standards activities.

Participatory framework

Methods and instruments used, taking into account the feedback and experience from T1.2 and T2.2.

Business plans

Roadmap for further exploitation of QROWD results.

Requirements and architecture

Report on the requirements for QROWD platform and architecture describing the integrated platform.

Exploitation strategy

Includes IPR, usage policies, measures to manage/protect the QROWD IP for its further exploitation, potential business models.

Data catalog

This deliverable describes the outcomes of T4.1 related to dataset identification and data acquisition requirement analysis. It includes a description and assessment of available datasets and of the datasets that needs to be generated by crowdsourcing services as well as a selection of the tools and techniques needed in order to inject those data sources into the QROWD workflow.


This report will contain information on the datasets converted and integrated in T1.1.


Results of the hackathon with recommendations to the WP1 pilot.

Benchmarking registry, reporting, and crowdsourcing monitoring tools

Benchmark components, initial setup and the registry alongside the instruments used to monitor crowd performance.

Ideas competition

Report of the competition results, including aspects of stakeholder collaborations as well as recommendations on the inclusion of results in the WP1 pilot.

Public endpoints and deployment

Final version of the crowdsourcing middleware prototype with a comprehensive set of connected public services for demonstrations.

Data quality assessment services

This report describes crowdsourcing-enabled link quality assessment methods and adaptation of the respective crowdsourcing component of Entitypedia.

Link discovery and data fusion algorithms

Crowdsourcing-enabled link discovery algorithms including large-scale evaluation with cloud based link discovery connected to QROWD (T5.1) In addition, this deliverable includes the crowdsourcing-enabled data fusion algorithms, including large-scale evaluation involving cloud based data fusion connected to QROWD services (T5.2). This deliverable will contribute to existing data interoperability and standards activities within W3C.

Data management plan

Data management plan (R, M6)

Crowdsourcing vocabulary and licensing

Report to document the developed crowdsourcing vocabulary and licensing recommendations. This deliverable will propose standards for data exchange and interoperability in crowdsourcing.

Searching for OpenAIRE data...


Assessing Consistency of in the wild Annotations

Author(s): F. Giunchiglia, E. Bignotti, M. Zeni, and Wanyi Zhang
Published in: 2nd International Workshop on Annotation of useR Data for UbiquitOUs Systems, 2018

Efficiently Pinpointing SPARQL Query Containments

Author(s): Claus Stadler, Muhammad Saleem, Axel-Cyrille Ngonga Ngomo, Jens Lehmann
Published in: 2018, Page(s) 210-224
DOI: 10.1007/978-3-319-91662-0_16

Combining Crowdsourcing and Crowdsensing to Infer the Spatial Context

Author(s): F. Giunchiglia, E. Bignotti, and M. Zeni
Published in: International Workshop on Context-Awareness for Multi-Device Pervasive and Mobile Computing, 2018

Mobile Social Media and Academic Performance

Author(s): Fausto Giunchiglia, Mattia Zeni, Elisa Gobbi, Enrico Bignotti, Ivano Bison
Published in: 2017, Page(s) 3-13
DOI: 10.1007/978-3-319-67256-4_1

Personal Context Recognition via Reliable Human-Machine Collaboration

Author(s): F. Giunchiglia, M. Zeni, E. Bignotti
Published in: Workshop on Information Quality and Quality of Service for Pervasive Computing, 2018

Hybrid Human Machine workflows for mobility management

Author(s): Eddy Maddalena, Luis-Daniel Ibáñez, Elena Simperl, Richard Gomer, Mattia Zeni, Donglei Song, Fausto Giunchiglia
Published in: Companion Proceedings of The 2019 World Wide Web Conference on - WWW '19, 2019, Page(s) 102-109
DOI: 10.1145/3308560.3317056

Querying Large-scale RDF Datasets Using the SANSA Framework

Author(s): Stadler, Claus; Sejdiu, Gezim; Graux, Damian; Lehmann, Jens
Published in: Proceedings of the ISWC 2019 Satellite Tracks (Posters & Demonstrations, Industry, and Outrageous Ideas), 2019
DOI: 10.5281/zenodo.3567886

SPIRIT: A Semantic Transparency and Compliance Stack

Author(s): Westphal, Patrick; Fernández, Javier D.; Kirrane, Sabrina; Lehmann, Jens
Published in: 2018
DOI: 10.5281/zenodo.3567866

QROWD: Because Big Data Integration is Humanly Possible

Author(s): Maddalena, Eddy; Ibáñez, Luis-Daniel; Simperl, Elena; Zeni, Mattia; Bignotti, Enrico; Giunchiglia, Fausto; Stadler, Claus; Westphal, Patrick; Garcia, Luis P.F.; Lehmann, Jens
Published in: 2018
DOI: 10.5281/zenodo.3568169

How Biased Is Your NLG Evaluation?

Author(s): Vougiouklis, Pavlos; Maddalena, Eddy; Hare, Jonathon; Simperl, Elena
Published in: Joint Proceedings SAD 2018 and CrowdBias 2018, 2018
DOI: 10.5281/zenodo.3568173

Personal Context Recognition Via Reliable Human-Machine Collaboration

Author(s): Fausto Giunchiglia, Mattia Zeni, Enrico Big
Published in: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2018, Page(s) 379-384
DOI: 10.1109/percomw.2018.8480307

Combining Crowdsourcing and Crowdsensing to Infer the Spatial Context

Author(s): Mattia Zeni, Enrico Bignotti, Fausto Giunchiglia
Published in: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2018, Page(s) 28-33
DOI: 10.1109/percomw.2018.8480312

SML-Bench -- A Benchmarking Framework for Structured Machine Learning

Author(s): Patrick Westphal Lorenz Bühmann Simon Bin Hajira Jabeen Jens Lehmann
Published in: Semantic Web – Interoperability, Usability, Applicability, 2018, ISSN 1570-0844

Human-Like Context Sensing for Robot Surveillance

Author(s): Fausto Giunchiglia, Enrico Bignotti, Mattia Zeni
Published in: International Journal of Semantic Computing, Issue 12/01, 2018, Page(s) 129-148, ISSN 1793-7108
DOI: 10.1142/s1793351x1840007x

Beyond Monetary Incentives

Author(s): Oluwaseyi Feyisetan, Elena Simperl
Published in: ACM Transactions on Social Computing, Issue 2/2, 2019, Page(s) 1-31, ISSN 2469-7818
DOI: 10.1145/3321700

SML-Bench – A benchmarking framework for structured machine learning

Author(s): Patrick Westphal, Lorenz Bühmann, Simon Bin, Hajira Jabeen, Jens Lehmann
Published in: Semantic Web, Issue 10/2, 2019, Page(s) 231-245, ISSN 1570-0844
DOI: 10.3233/sw-180308

Towards a Scalable Semantic-Based Distributed Approach for SPARQL Query Evaluation

Author(s): Gezim Sejdiu, Damien Graux, Imran Khan, Ioanna Lytra, Hajira Jabeen, Jens Lehmann
Published in: Semantic Systems. The Power of AI and Knowledge Graphs - 15th International Conference, SEMANTiCS 2019, Karlsruhe, Germany, September 9–12, 2019, Proceedings, Issue 11702, 2019, Page(s) 295-309
DOI: 10.1007/978-3-030-33220-4_22

DistLODStats: Distributed Computation of RDF Dataset Statistics

Author(s): Gezim Sejdiu, Ivan Ermilov, Jens Lehmann, Mohamed Nadjib Mami
Published in: The Semantic Web – ISWC 2018 - 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018, Proceedings, Part II, Issue 11137, 2018, Page(s) 206-222
DOI: 10.1007/978-3-030-00668-6_13

A Scalable Framework for Quality Assessment of RDF Datasets

Author(s): Gezim Sejdiu, Anisa Rula, Jens Lehmann, Hajira Jabeen
Published in: The Semantic Web – ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26–30, 2019, Proceedings, Part II, Issue 11779, 2019, Page(s) 261-276
DOI: 10.1007/978-3-030-30796-7_17

On the mapping of Points of Interest through StreetView Imagery and paid crowdsourcing

Author(s): Maddalena, Eddy; Ibáñez, Luis-Daniel; Simperl, Elena
Published in: 2018
DOI: 10.5281/zenodo.3568200